[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v4 07/12] migration: not wait RDMA_CM_EVENT_DISC
From: |
Dr. David Alan Gilbert |
Subject: |
Re: [Qemu-devel] [PATCH v4 07/12] migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect |
Date: |
Wed, 30 May 2018 13:24:18 +0100 |
User-agent: |
Mutt/1.9.5 (2018-04-13) |
* Lidong Chen (address@hidden) wrote:
> From: Lidong Chen <address@hidden>
>
> When cancel migration during RDMA precopy, the source qemu main thread hangs
> sometime.
>
> The backtrace is:
> (gdb) bt
> #0 0x00007f249eabd43d in write () from /lib64/libpthread.so.0
> #1 0x00007f24a1ce98e4 in rdma_get_cm_event (channel=0x4675d10,
> event=0x7ffe2f643dd0) at src/cma.c:2189
> #2 0x00000000007b6166 in qemu_rdma_cleanup (rdma=0x6784000) at
> migration/rdma.c:2296
> #3 0x00000000007b7cae in qio_channel_rdma_close (ioc=0x3bfcc30,
> errp=0x0) at migration/rdma.c:2999
> #4 0x00000000008db60e in qio_channel_close (ioc=0x3bfcc30, errp=0x0) at
> io/channel.c:273
> #5 0x00000000007a8765 in channel_close (opaque=0x3bfcc30) at
> migration/qemu-file-channel.c:98
> #6 0x00000000007a71f9 in qemu_fclose (f=0x527c000) at
> migration/qemu-file.c:334
> #7 0x0000000000795b96 in migrate_fd_cleanup (opaque=0x3b46280) at
> migration/migration.c:1162
> #8 0x000000000093a71b in aio_bh_call (bh=0x3db7a20) at util/async.c:90
> #9 0x000000000093a7b2 in aio_bh_poll (ctx=0x3b121c0) at util/async.c:118
> #10 0x000000000093f2ad in aio_dispatch (ctx=0x3b121c0) at
> util/aio-posix.c:436
> #11 0x000000000093ab41 in aio_ctx_dispatch (source=0x3b121c0,
> callback=0x0, user_data=0x0)
> at util/async.c:261
> #12 0x00007f249f73c7aa in g_main_context_dispatch () from
> /lib64/libglib-2.0.so.0
> #13 0x000000000093dc5e in glib_pollfds_poll () at util/main-loop.c:215
> #14 0x000000000093dd4e in os_host_main_loop_wait (timeout=28000000) at
> util/main-loop.c:263
> #15 0x000000000093de05 in main_loop_wait (nonblocking=0) at
> util/main-loop.c:522
> #16 0x00000000005bc6a5 in main_loop () at vl.c:1944
> #17 0x00000000005c39b5 in main (argc=56, argv=0x7ffe2f6443f8,
> envp=0x3ad0030) at vl.c:4752
>
> It does not get the RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect
> sometime.
>
> According to IB Spec once active side send DREQ message, it should wait for
> DREP message
> and only once it arrived it should trigger a DISCONNECT event. DREP message
> can be dropped
> due to network issues.
> For that case the spec defines a DREP_timeout state in the CM state machine,
> if the DREP is
> dropped we should get a timeout and a TIMEWAIT_EXIT event will be trigger.
> Unfortunately the current kernel CM implementation doesn't include the
> DREP_timeout state
> and in above scenario we will not get DISCONNECT or TIMEWAIT_EXIT events.
>
> So it should not invoke rdma_get_cm_event which may hang forever, and the
> event channel
> is also destroyed in qemu_rdma_cleanup.
>
> Signed-off-by: Lidong Chen <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
> ---
> migration/rdma.c | 12 ++----------
> migration/trace-events | 1 -
> 2 files changed, 2 insertions(+), 11 deletions(-)
>
> diff --git a/migration/rdma.c b/migration/rdma.c
> index 0dd4033..92e4d30 100644
> --- a/migration/rdma.c
> +++ b/migration/rdma.c
> @@ -2275,8 +2275,7 @@ static int qemu_rdma_write(QEMUFile *f, RDMAContext
> *rdma,
>
> static void qemu_rdma_cleanup(RDMAContext *rdma)
> {
> - struct rdma_cm_event *cm_event;
> - int ret, idx;
> + int idx;
>
> if (rdma->cm_id && rdma->connected) {
> if ((rdma->error_state ||
> @@ -2290,14 +2289,7 @@ static void qemu_rdma_cleanup(RDMAContext *rdma)
> qemu_rdma_post_send_control(rdma, NULL, &head);
> }
>
> - ret = rdma_disconnect(rdma->cm_id);
> - if (!ret) {
> - trace_qemu_rdma_cleanup_waiting_for_disconnect();
> - ret = rdma_get_cm_event(rdma->channel, &cm_event);
> - if (!ret) {
> - rdma_ack_cm_event(cm_event);
> - }
> - }
> + rdma_disconnect(rdma->cm_id);
> trace_qemu_rdma_cleanup_disconnect();
> rdma->connected = false;
> }
> diff --git a/migration/trace-events b/migration/trace-events
> index 3c798dd..4a768ea 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -146,7 +146,6 @@ qemu_rdma_accept_pin_state(bool pin) "%d"
> qemu_rdma_accept_pin_verbsc(void *verbs) "Verbs context after listen: %p"
> qemu_rdma_block_for_wrid_miss(const char *wcompstr, int wcomp, const char
> *gcompstr, uint64_t req) "A Wanted wrid %s (%d) but got %s (%" PRIu64 ")"
> qemu_rdma_cleanup_disconnect(void) ""
> -qemu_rdma_cleanup_waiting_for_disconnect(void) ""
> qemu_rdma_close(void) ""
> qemu_rdma_connect_pin_all_requested(void) ""
> qemu_rdma_connect_pin_all_outcome(bool pin) "%d"
> --
> 1.8.3.1
>
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK
- [Qemu-devel] [PATCH v4 01/12] migration: disable RDMA WRITE after postcopy started, (continued)
- [Qemu-devel] [PATCH v4 06/12] migration: Stop rdma yielding during incoming postcopy, Lidong Chen, 2018/05/30
- [Qemu-devel] [PATCH v4 05/12] migration: implement bi-directional RDMA QIOChannel, Lidong Chen, 2018/05/30
- [Qemu-devel] [PATCH v4 07/12] migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect, Lidong Chen, 2018/05/30
- Re: [Qemu-devel] [PATCH v4 07/12] migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect,
Dr. David Alan Gilbert <=
- [Qemu-devel] [PATCH v4 08/12] migration: implement io_set_aio_fd_handler function for RDMA QIOChannel, Lidong Chen, 2018/05/30
- [Qemu-devel] [PATCH v4 09/12] migration: invoke qio_channel_yield only when qemu_in_coroutine(), Lidong Chen, 2018/05/30
- [Qemu-devel] [PATCH v4 11/12] migration: poll the cm event while wait RDMA work request completion, Lidong Chen, 2018/05/30
- [Qemu-devel] [PATCH v4 10/12] migration: create a dedicated thread to release rdma resource, Lidong Chen, 2018/05/30